< Back to previous page

Project

Understanding ideological bias through data-driven methods: testing cognitive social learning processes through intersectional analysis of past data (c.1800-c.1940)

Ideological bias concerning age, gender, ethnicity and social class is a major ethical concern in contemporary society, influencing human behaviour both at macro- and micro-levels. Recent studies have demonstrated that machine learning methods (from artificial intelligence) not only capture, but amplify the ideological biases in the data they are trained on. In this project, we aim to strategically turn this undesirable property to our advantage and exploit the study of ideological biases for visual cultures in the nineteenth and early twentieth centuries (c.1800-c.1940). Recent cognitive studies make clear how ideological biases largely result from processes of social learning. To study the construction and dissemination of ideological bias we put forth three case studies in crucial areas of social control: education (children's literature), mass communication (magic lantern slides and performances), and regulation (police reports). These interlinked areas of study come with a wealth of rights-free digitized material and pre-existing scholarship. Through the application of standard routines from machine learning, we aim to elicit implicit patterns and trends relating to ideological bias and confront these with received knowledge. The current project is innovative in its methodology through its study of pixel data through computer vision in the humanities which has received too little attention so far. Moreover, it uses data-driven technology to present a novel intersectional viewpoint on the construction of ideological bias in the past. Finally, by being embedded in recent cognitive studies, the project will be able to make claims on how implicit bias functioned in the past, understanding better what people thought and how such thinking structured behavioural interactions with their surrounding world.
Date:1 Jan 2021 →  Today
Keywords:IMPLICIT BIAS
Disciplines:Literatures in Dutch, Literary history, Philosophy of mind, Iconology, Visual cultures